关于通过提示创建对话代理人格有效性的研究
On the Effectiveness of Creating Conversational Agent Personalities Through Prompting
AI总结：
本研究通过提示为GPT-3.5和GPT-4创建八种对话代理人格，利用LIWC分析发现多数语言线索可区分，提示方法需改进以支持持久人格塑造。
摘要：
在本工作中，我们报告了通过提示来定制基于GPT-3.5和GPT-4的对话代理的人格和对话风格的效果。我们使用三个人格维度，每个维度有两个水平，创建了八个对话代理原型。每个聊天机器人收集了十段对话，每段包含十个交流回合，在GPT-3.5和GPT-4上共生成1600个交流回合。使用语言查询与词频（LIWC）分析，我们比较了八个代理在语言元素上的差异，包括影响力、真实性和情感。在GPT-3.5中，有四个语言线索显著区分，而在GPT-4中有十二个显著区分。在LIWC总共十九个线索中，有十三个出现显著区分，我们的结果表明可能需要新颖的提示方法，以更好地适应持久对话代理人格或语言风格的创建和评估。
英文摘要：
In this work, we report on the effectiveness of our efforts to tailor the personality and conversational style of a conversational agent based on GPT-3.5 and GPT-4 through prompts. We use three personality dimensions with two levels each to create eight conversational agents archetypes. Ten conversations were collected per chatbot, of ten exchanges each, generating 1600 exchanges across GPT-3.5 and GPT-4. Using Linguistic Inquiry and Word Count (LIWC) analysis, we compared the eight agents on language elements including clout, authenticity, and emotion. Four language cues were significantly distinguishing in GPT-3.5, while twelve were distinguishing in GPT-4. With thirteen out of a total nineteen cues in LIWC appearing as significantly distinguishing, our results suggest possible novel prompting approaches may be needed to better suit the creation and evaluation of persistent conversational agent personalities or language styles.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
